Detecting Emotional Context for Safer Digital Mental Health Agents
Date
Authors
Supervisor
Item type
Journal Article
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
IOS Press
Abstract
Digital tools for mental health show great promise, but concerns arise when they fail to recognize the user state. We train a classifier to detect the emotional context of dialogs among 6 categories, achieving 78% accuracy on top choice. Importantly greatest areas of confusion (excited-hopeful, angry-sad) are not of the most unsafe kind. Such a classifier could serve as a resource to the dialog managers of future digital mental health agents.Description
Keywords
Dialog agents, empathetic computing, e-therapy, machine learning, Dialog agents, e-therapy, empathetic computing, machine learning, 4203 Health Services and Systems, 42 Health Sciences, Mental Health, Mental health, 3 Good Health and Well Being, 0807 Library and Information Studies, 1117 Public Health and Health Services, Medical Informatics, 4203 Health services and systems, 4601 Applied computing
Source
Studies in Health Technology and Informatics, ISSN: 0926-9630 (Print); 0926-9630 (Online), IOS Press, 310, 1442-1443. doi: 10.3233/SHTI231235